# Adversarial Bandits and the Exp3 Algorithm

DevFeed: [Adversarial Bandits and the Exp3 Algorithm](<https://devfeed.tech/articles/adversarial-bandits-and-the-exp3-algorithm-40333.md>)

Original publisher: [Read original article](<https://www.jeremykun.com/2013/11/08/adversarial-bandits-and-the-exp3-algorithm/>)

Published: 2013-11-08T09:00:40Z

Content type: tutorial

Language: en

Sources: [Jeremy Kun](<https://devfeed.tech/sources/jeremy-kun.md>)

Topics: [Machine Learning & Artificial Intelligence](<https://devfeed.tech/topics/machine-learning-artificial-intelligence.md>), [Algorithm](<https://devfeed.tech/topics/algorithm.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [bandit-learning](<https://devfeed.tech/tags/bandit-learning.md>), [bandits](<https://devfeed.tech/tags/bandits.md>), [exp3](<https://devfeed.tech/tags/exp3.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mathematics](<https://devfeed.tech/tags/mathematics.md>), [multiplicative-weights-update-algorithm](<https://devfeed.tech/tags/multiplicative-weights-update-algorithm.md>), [programming](<https://devfeed.tech/tags/programming.md>), [python](<https://devfeed.tech/tags/python.md>)

## AI overview

This article introduces adversarial bandit learning and explains how the Exp3 algorithm addresses decisions with uncertain outcomes. It contrasts adversarial payoffs with the simpler stochastic setting and frames success relative to the best single action over repeated trials.

## Source excerpt

In the last twenty years there has been a lot of research in a subfield of machine learning called Bandit Learning. The name comes from the problem of being faced with a large sequence of slot machines (once called one-armed bandits) each with a potentially different payout scheme. The problems in this field all focus on one central question: If I have many available actions with uncertain outcomes, how should I act to maximize the quality of my results over many trials?